# scrapi MCP server

Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-bamchi-scrapi
- Repository: https://github.com/bamchi/scrapi-mcp-server

## Install
- Command: `npx -y @scrapi.ai/mcp-server`
- Endpoint: https://scrapi.ai/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization
- Package: Npm @scrapi.ai/mcp-server v2.0.6
- Environment variable: SCRAPI_API_KEY (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://scrapi.ai/mcp
- Header: Authorization

## Tools
- scrape_url - Scrapes a webpage and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering. Endpoint: https://scrapi.ai/mcp
- scrape_urls - Scrapes multiple webpages in parallel and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering. Endpoint: https://scrapi.ai/mcp
- get_usage - Check API usage and remaining credits. Returns current plan, subscription credits, purchased credits, and total remaining credits. Endpoint: https://scrapi.ai/mcp
- scraper_server_status - Check the status of all ScraperServer instances. Shows server health, circuit breaker state, failure counts, and last success/failure times. Endpoint: https://scrapi.ai/mcp
- get_billing - Retrieve MCP billing information: subscription details, available plans, daily usage history, or spending limits. Endpoint: https://scrapi.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.bamchi
- Version: 2.0.6
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Feb 12, 2026
- Source: https://registry.modelcontextprotocol.io